| name | benchmark |
| description | Run evaluation benchmarks and report precision/recall |
| allowed-tools | Bash, Read |
| argument-hint | ["--save"] |
python3 scripts/quality/benchmark_cairo_auditor.py --cases evals/cases/cairo_auditor_benchmark.jsonl --output /tmp/bench-auditor.md --min-precision 0.90 --min-recall 0.90python3 scripts/quality/benchmark_contract_skills.py --cases evals/cases/contract_skill_benchmark.jsonl --output /tmp/bench-contracts.md --min-precision 0.95 --min-recall 0.95$ARGUMENTS contains --save, append --save to both commands to copy scorecards into evals/scorecards/.Routes Cairo/Starknet coding and audit tasks to the smallest relevant module for focused, high-quality execution.
Cairo smart-contract authoring on Starknet. Trigger on "write a contract", "create a contract", "implement this in Cairo", "add storage/events/interface", "compose components". Guides structure, security patterns, and component wiring.
Improves Cairo performance after correctness is established. Trigger on "optimize", "gas usage", "reduce steps", "profile", "BoundedInt", "storage packing", "benchmark". Guides profiling, arithmetic optimization, and bounded-int hardening.
Cairo smart-contract testing with snforge. Trigger on "write tests", "add unit tests", "fuzz test", "integration test", "test this contract", "regression test". Guides test strategy, cheatcode usage, and coverage.
Covers Starknet build, declare, deploy, verify, and release operations with a deterministic workflow and command-level references.
Security audit of Cairo/Starknet code. Trigger on "audit", "check this contract", "review for security". Modes - default (full repo), deep (+ adversarial reasoning), or specific filenames.